You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We have benchmark.py for evaluating the performance of different sampler methods over a GeoDataset. Currently benchmark.py works with a ZipDataset of Landsat 8 imagery and CDL labels. Generally, we want TorchGeo to be able to sample arbitrary patches of data from GeoDatasets as quickly as possible.
There are several GeoDatasets cases that we need to consider:
When both reprojection and resampling need to be done
When only resampling needs to be done
When neither needs to be done
This issue is to track the performance of these cases.
The text was updated successfully, but these errors were encountered:
We have
benchmark.py
for evaluating the performance of different sampler methods over aGeoDataset
. Currentlybenchmark.py
works with a ZipDataset of Landsat 8 imagery and CDL labels. Generally, we want TorchGeo to be able to sample arbitrary patches of data from GeoDatasets as quickly as possible.There are several GeoDatasets cases that we need to consider:
This issue is to track the performance of these cases.
The text was updated successfully, but these errors were encountered: